{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZHPTBPXA6GBY3DWV35WRP6EXA6","short_pith_number":"pith:ZHPTBPXA","canonical_record":{"source":{"id":"1805.08394","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-05-22T05:10:13Z","cross_cats_sorted":[],"title_canon_sha256":"5b6e24bb9c2da5edef54db5741ac50fa8002e9d1e805e74394c725f1bd7a12ea","abstract_canon_sha256":"dbb732d4319451dea2571e90f3e9c3e607ac66463227f9f4e9b3d357f209beb4"},"schema_version":"1.0"},"canonical_sha256":"c9df30bee0f1838d8ed5df6d17f897078aa68500e6efdb98bf9db576fb2d3cf8","source":{"kind":"arxiv","id":"1805.08394","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08394","created_at":"2026-05-18T00:14:53Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08394v2","created_at":"2026-05-18T00:14:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08394","created_at":"2026-05-18T00:14:53Z"},{"alias_kind":"pith_short_12","alias_value":"ZHPTBPXA6GBY","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZHPTBPXA6GBY3DWV","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZHPTBPXA","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZHPTBPXA6GBY3DWV35WRP6EXA6","target":"record","payload":{"canonical_record":{"source":{"id":"1805.08394","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-05-22T05:10:13Z","cross_cats_sorted":[],"title_canon_sha256":"5b6e24bb9c2da5edef54db5741ac50fa8002e9d1e805e74394c725f1bd7a12ea","abstract_canon_sha256":"dbb732d4319451dea2571e90f3e9c3e607ac66463227f9f4e9b3d357f209beb4"},"schema_version":"1.0"},"canonical_sha256":"c9df30bee0f1838d8ed5df6d17f897078aa68500e6efdb98bf9db576fb2d3cf8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:53.150827Z","signature_b64":"UkAlEcFu4XfebFuRIZnduUfgnLHOg1W82UAKRO6NaUKxDxMW6JAwyBIiaT5bNGmcJ8Vu/Zcp53Z96uCvADg/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9df30bee0f1838d8ed5df6d17f897078aa68500e6efdb98bf9db576fb2d3cf8","last_reissued_at":"2026-05-18T00:14:53.150264Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:53.150264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.08394","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VnipFKo2h1RxBSMnp+nxtT2k5ZkR/FeNTzDGwduVA+skYXEPNJuWSmgPCCjSjASjP22UNekfWw7HEOj07RehAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:58:35.605797Z"},"content_sha256":"98abd7c249e84a01231b2d44cea3ce09b9f59b101380b37ed2e4a810fdf675ba","schema_version":"1.0","event_id":"sha256:98abd7c249e84a01231b2d44cea3ce09b9f59b101380b37ed2e4a810fdf675ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZHPTBPXA6GBY3DWV35WRP6EXA6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"State-Denoised Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Denis Kazakov, Michael C.Mozer, Robert V. Lindsey","submitted_at":"2018-05-22T05:10:13Z","abstract_excerpt":"Recurrent neural networks (RNNs) are difficult to train on sequence processing tasks, not only because input noise may be amplified through feedback, but also because any inaccuracy in the weights has similar consequences as input noise. We describe a method for denoising the hidden state during training to achieve more robust representations thereby improving generalization performance. Attractor dynamics are incorporated into the hidden state to `clean up' representations at each step of a sequence. The attractor dynamics are trained through an auxillary denoising loss to recover previously "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08394","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:14:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JLIBMTrnYrFvh99N179xzWWRoSF8tuhrx2drNpY/GzO3zTMArQ5ffjxPaZ4wY1na8ZOzxqbrFfTSOjO0whR2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:58:35.606134Z"},"content_sha256":"961eb9ba7eff7394177a0b7d7e6801c17c323208c73851e7ccfdc39ca608335f","schema_version":"1.0","event_id":"sha256:961eb9ba7eff7394177a0b7d7e6801c17c323208c73851e7ccfdc39ca608335f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZHPTBPXA6GBY3DWV35WRP6EXA6/bundle.json","state_url":"https://pith.science/pith/ZHPTBPXA6GBY3DWV35WRP6EXA6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZHPTBPXA6GBY3DWV35WRP6EXA6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T13:58:35Z","links":{"resolver":"https://pith.science/pith/ZHPTBPXA6GBY3DWV35WRP6EXA6","bundle":"https://pith.science/pith/ZHPTBPXA6GBY3DWV35WRP6EXA6/bundle.json","state":"https://pith.science/pith/ZHPTBPXA6GBY3DWV35WRP6EXA6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZHPTBPXA6GBY3DWV35WRP6EXA6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZHPTBPXA6GBY3DWV35WRP6EXA6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dbb732d4319451dea2571e90f3e9c3e607ac66463227f9f4e9b3d357f209beb4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-05-22T05:10:13Z","title_canon_sha256":"5b6e24bb9c2da5edef54db5741ac50fa8002e9d1e805e74394c725f1bd7a12ea"},"schema_version":"1.0","source":{"id":"1805.08394","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08394","created_at":"2026-05-18T00:14:53Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08394v2","created_at":"2026-05-18T00:14:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08394","created_at":"2026-05-18T00:14:53Z"},{"alias_kind":"pith_short_12","alias_value":"ZHPTBPXA6GBY","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZHPTBPXA6GBY3DWV","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZHPTBPXA","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:961eb9ba7eff7394177a0b7d7e6801c17c323208c73851e7ccfdc39ca608335f","target":"graph","created_at":"2026-05-18T00:14:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Recurrent neural networks (RNNs) are difficult to train on sequence processing tasks, not only because input noise may be amplified through feedback, but also because any inaccuracy in the weights has similar consequences as input noise. We describe a method for denoising the hidden state during training to achieve more robust representations thereby improving generalization performance. Attractor dynamics are incorporated into the hidden state to `clean up' representations at each step of a sequence. The attractor dynamics are trained through an auxillary denoising loss to recover previously ","authors_text":"Denis Kazakov, Michael C.Mozer, Robert V. Lindsey","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-05-22T05:10:13Z","title":"State-Denoised Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08394","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:98abd7c249e84a01231b2d44cea3ce09b9f59b101380b37ed2e4a810fdf675ba","target":"record","created_at":"2026-05-18T00:14:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dbb732d4319451dea2571e90f3e9c3e607ac66463227f9f4e9b3d357f209beb4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-05-22T05:10:13Z","title_canon_sha256":"5b6e24bb9c2da5edef54db5741ac50fa8002e9d1e805e74394c725f1bd7a12ea"},"schema_version":"1.0","source":{"id":"1805.08394","kind":"arxiv","version":2}},"canonical_sha256":"c9df30bee0f1838d8ed5df6d17f897078aa68500e6efdb98bf9db576fb2d3cf8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9df30bee0f1838d8ed5df6d17f897078aa68500e6efdb98bf9db576fb2d3cf8","first_computed_at":"2026-05-18T00:14:53.150264Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:53.150264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UkAlEcFu4XfebFuRIZnduUfgnLHOg1W82UAKRO6NaUKxDxMW6JAwyBIiaT5bNGmcJ8Vu/Zcp53Z96uCvADg/Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:53.150827Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.08394","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98abd7c249e84a01231b2d44cea3ce09b9f59b101380b37ed2e4a810fdf675ba","sha256:961eb9ba7eff7394177a0b7d7e6801c17c323208c73851e7ccfdc39ca608335f"],"state_sha256":"3b45a013d623e18dd592b75fdd980c600a9c0b5ca69e1c9b71e699c09dda3aa4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h+MuTHf7cGBVZ5anSefRpnp0zeUKAuaRqmpbCDQYHVudLqwkL1gz9CJd9Sr6ZVGsFSw7rBF8wXfpNAnoWF6OCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T13:58:35.608166Z","bundle_sha256":"b10882aaacc86dca5b7af3aa0a7c50fe13775561419f26606ecd8049b02e1427"}}